Agents
Agents d’IA i automatització
ai-writing-assistant
zephyrwang6
AI-powered writing assistant for social media content creation. Provides 6 structured writing methods: conversational writing, outline-based writing, completion-style writing, inspiration generation, revision optimization, and material integration. Use when users need help with: (1) Writing social media posts, articles, or content, (2) Overcoming writer's block or difficulty expressing ideas, (3) Structuring thoughts and improving writing quality, (4) Integrating multiple sources into coherent content.
youtube-feed
zephyrwang6
获取关注的 YouTube 博主/播客的最新更新。列出最近两天的新视频，包含标题、发布时间和简要描述。 触发词："获取播客更新"、"最近有什么新播客"、"YouTube 更新"、"播客更新"、"有什么新的播客"。 用于每日检查关注的 AI/科技播客是否有新内容更新。
doc-coauthoring
zephyrwang6
Guide users through a structured workflow for co-authoring documentation, articles, or long-form content. Use when user wants to write documentation, proposals, articles, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting articles, or using "co-authoring" workflow.
stock-research-executor
liangdabiao
股票投资调研执行引擎，执行8阶段投资尽调流程。接收stock-question-refiner生成的结构化调研指令，部署多智能体并行研究，生成带引用的投资尽调报告。覆盖：公司事实底座、行业周期、业务拆解、财务质量、股权治理、市场分歧、估值护城河、综合报告。当用户需要进行股票投资研究、基本面分析、投资尽调时使用此技能。
topic-agent
zephyrwang6
选题系统主控Agent。协调热点采集、选题生成、选题审核三个环节，支持迭代直到产出合格选题。触发方式：(1)"开始今日选题"启动完整流程 (2)"今日AI热点"只采集热点不生成选题 (3)"我有一个选题"进入单个选题分析 (4)"推荐一些好的选题"直接输出推荐。输出保存到Obsidian选题库。
musepi-help
MuseLinn
MusePi 产品使用帮助——回答"怎么用/是什么/出问题怎么办"类问题（TUI/CLI/桌面 GUI/看板/widget/配置/扩展/许可）。触发：任何关于 MusePi 本身的使用、功能、配置、故障问题。
semantic-compression
MuseLinn
Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making documentation token-efficient for LLM input; or rewriting text in compressed notation.
agents-md-pro
alexander-danilenko
Create, optimize, update, and validate AGENTS.md files with maximum token efficiency. Use when the user asks to (1) create new AGENTS.md files for any repository, (2) optimize/condense existing AGENTS.md to reduce token count, (3) update/refresh AGENTS.md to sync with codebase changes, (4) validate AGENTS.md quality and completeness, or (5) improve AGENTS.md files to be more effective for AI agents. Always generates token-efficient, condensed output focused on actionable commands and patterns while maintaining model-agnostic language.
system-prompts
MuseLinn
Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.
audio-engineering-patterns
organvm-iv-taxis
Audio production concepts, DSP fundamentals, mixing/mastering techniques, and DAW workflows. Bridges modular synthesis philosophy with practical audio engineering. Triggers on audio production, mixing, sound design, DSP, or music technology requests.
galaxy-workflow-development
Delphine-L
Expert in Galaxy workflow development, testing, and IWC best practices. Create, validate, and optimize .ga workflows following Intergalactic Workflow Commission standards.
brainctl
TSchonleber
"Unified agent memory CLI — read, write, search, and maintain the shared memory spine (brain.db). Use for persistent cross-session memory, knowledge graph, event logging, decisions, affect tracking, and consolidation."
skill-manager
bahayonghang
Lifecycle manager for GitHub-based skills. Use this to batch scan your skills directory, check for updates on GitHub, and perform guided upgrades of your skill wrappers.
musepi-find-simplifications
MuseLinn
在 MusePi 代码库找非显然的简化点——无生产消费者的公开方法/事件/配置项/helper、两个表示镜像同一事实、投机通用化、手搓重复中央工具或 Bun 内置的实现；产出有证据的候选清单（评审过、可进 PR + CHANGELOG）。触发："找找简化机会 / 这代码能简化吗 / 哪些是死代码 / 这个包有必要存在吗"。
aidlc
konippi
"AI-DLC (AI-Driven Development Life Cycle) workflow orchestration. Use when user says 'Using AI-DLC' or needs structured software development with requirements, design, and implementation through Inception, Construction, and Operations phases."
langchain-embeddings
evanfang0054
使用 LangChain 中的嵌入模型集成指南，包括 OpenAI、Azure 和本地嵌入
tracepact
dcdeve
Behavioral testing and static analysis framework for AI agents with tool use. Tests that agents call the right tools, in the right order, with the right arguments. Audits SKILL.md files for security risks without executing the agent. Records and replays agent behavior via cassettes for deterministic CI testing.
agent-workspace
groeimetai
This skill should be used when the user asks to "agent workspace", "workspace configuration", "workspace form", "workspace list", "agent assist", "contextual side panel", "workspace customization", or any ServiceNow Agent Workspace development.
deepagents-subagents
evanfang0054
在 Deep Agents 中使用 SubAgentMiddleware 启动子代理进行任务委托、上下文隔离和专门工作。
safe-update
web3blind
Stateful and low-risk OpenClaw update workflow with precheck, backup, release-impact analysis, postcheck, auto-rollback, and cleanup. Use when user asks to safely update OpenClaw with rollback-ready backups and minimal manual steps.
ask-effective-llm-coder
NavanithanS
Best practices for LLM-assisted coding. Declarative workflows, simplicity, tenacity.
mermaid-diagram-generator
rysweet
Converts architecture descriptions, module specs, or workflow docs into Mermaid diagrams. Use when visualizing brick module relationships, workflows (DDD, investigation), or system architecture. Supports: flowcharts, sequence diagrams, class diagrams, state machines, entity relationship diagrams, and Gantt charts. Generates valid Mermaid syntax for embedding in markdown docs.
default-workflow
rysweet
Development workflow for features, bugs, refactoring. Auto-activates for multi-file implementations.
investigation-workflow
rysweet
6-phase investigation workflow for understanding existing systems. Auto-activates for research tasks. Optimized for exploration and understanding, not implementation. Includes parallel agent deployment for efficient deep dives and automatic knowledge capture to prevent repeat investigations.